GHSA-FG94-H982-F3MM Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

Because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrust...

PT-2026-50594

Name of the Vulnerable Software and Affected Versions Claude Code versions 0.2.54 through 2.1.162 Description Claude Code, an agentic coding tool, contains an issue where the hostname huggingface.co was pre-approved for the WebFetch tool. This allowed any path on that domain, including...

nanobot 代码问题漏洞

Nanobot is a lightweight personal AI assistant open-source by Data Intelligence Lab@HKU. Versions of Nanobot prior to 0.2.1 contained code vulnerabilities. These vulnerabilities stemmed from issues with server-side request forgeing in the webFetch tool. This could allow remote attackers to access...

Tencent WeKnora 代码问题漏洞

Tencent WeKnora is a LLM-based framework developed by Tencent China. It features deep document understanding using the RAG paradigm, semantic retrieval, and context-aware answers. Versions of Tencent WeKnora prior to 0.3.0 contained code vulnerabilities. These vulnerabilities were caused by a DNS...

CVE-2026-24052 Claude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled Domains

Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org,...

EUVD-2026-5172

Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org,...

CVE-2026-24052

Summary: CVE-2026-24052 affects Claude Code prior to 1.0.111, where URL validation in the trusted-domain check for WebFetch used a startsWith() approach, allowing crafted domains (e.g., modelcontextprotocol.io.example.com) to bypass validation and potentially cause automatic requests to attacker‑...

PT-2026-6486

Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org, modelcontextprotocol.io, this could have enabled attackers to register domains like...

CVE-2026-24052: URL Redirection to Untrusted Site

Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org,...

CVE-2026-0616

TheLibrarians webfetch tool can be used to retrieve the Adminer interface content, which can then be used to log into the internal TheLibrarian backend system. The vendor has fixed the vulnerability in all affected versions...

The Librarian security vulnerability

The Librarian is a personal AI assistant software developed by The Librarian Company in Singapore. The Librarian has a security vulnerability, which stems from an internal port scanning vulnerability in the webFetch tool. This vulnerability may allow scanning of internal IP addresses and services...

The Librarian security vulnerability

The Librarian is a personal AI assistant software developed by The Librarian Company in Singapore. The Librarian has a security vulnerability, which stems from an information leakage issue in the webFetch tool. This vulnerability could potentially be exploited to make requests through the The...

The Librarian security vulnerability

The Librarian is a personal AI assistant software developed by The Librarian Company in Singapore. The Librarian has a security vulnerability, which stems from the webFetch tool’s ability to retrieve Supervisory Server status pages, potentially leading to the exposure of backend running processes...

The Librarian security vulnerability

The Librarian is a personal AI assistant software developed by The Librarian Company in Singapore. The Librarian has a security vulnerability, which stems from the webFetch tool’s ability to retrieve content from the Adminer interface, potentially allowing access to internal backend systems...